Mapping the distribution of coniferous forests is of great importance to the sustainable management of forests and government decision-making. The development of remote sensing, cloud computing and deep learning has provided the support of data, computing power and algorithms for obtaining large-scale forest parameters. However, few studies have used deep learning algorithms combined with Google Earth Engine (GEE) to extract coniferous forests in large areas and the performance remains unknown. In this study, we thus propose a cloud-enabled deep-learning approach using long-time series Landsat remote sensing images to map the distribution and obtain information on the dynamics of coniferous forests over 35 years (1985–2020) in the northwest of Liaoning, China, through the combination of GEE and U²-Net. Firstly, to assess the reliability of the proposed method, the U²-Net model was compared with three Unet variants (i.e., Resnet50-Unet, Mobile-Unet and U-Net) in coniferous forest extraction. Secondly, we evaluated U²-Net’s temporal transferability of remote sensing images from Landsat-5 TM, Landsat-7 ETM+ and Landsat-8 OLI. Finally, we compared the results obtained by the proposed approach with three publicly available datasets, namely GlobeLand30-2010, GLC_FCS30-2010 and FROM_GLC30-2010. The results show that (1) the cloud-enabled deep-learning approach proposed in this paper that combines GEE and U²-Net achieves a high performance in coniferous forest extraction with an F1 score, overall accuracy (OA), precision, recall and kappa of 95.4%, 94.2%, 96.6%, 95.5% and 94.0%, respectively, outperforming the other three Unet variants; (2) the proposed model trained by the sample blocks collected from a specific time can be applied to predict the coniferous forests in different years with satisfactory precision; (3) Compared with three global land-cover products, the distribution of coniferous forests extracted by U²-Net was most similar to that of actual coniferous forests; (4) The area of coniferous forests in Northwestern Liaoning showed an upward trend in the past 35 years. The area of coniferous forests has grown from 945.64 km² in 1985 to 6084.55 km² in 2020 with a growth rate of 543.43%. This study indicates that the proposed approach combining GEE and U²-Net can extract coniferous forests quickly and accurately, which helps obtain dynamic information and assists scientists in developing sustainable strategies for forest management.

Information about the distribution of coniferous forests holds significance for enhancing forestry efficiency and making informed policy decisions. Accurately identifying and mapping coniferous forests can expedite the achievement of Sustainable Development Goal (SDG) 15, aimed at managing forests sustainably, combating desertification, halting and reversing land degradation, and halting biodiversity loss. However, traditional methods employed to identify and map coniferous forests are costly and labor-intensive, particularly in dealing with large-scale regions. Consequently, a methodological framework is proposed to identify coniferous forests in northwestern Liaoning, China, in which there are semi-arid and barren environment areas. This framework leverages a multi-classifier fusion algorithm that combines deep learning (U²-Net and Resnet-50) and shallow learning (support vector machines and random forests) methods deployed in the Google Earth Engine. Freely available remote sensing images are integrated from multiple sources, including Gaofen-1 and Sentinel-1, to enhance the accuracy and reliability of the results. The overall accuracy of the coniferous forest identification results reached 97.6%, highlighting the effectiveness of the proposed methodology. Further calculations were conducted to determine the area of coniferous forests in each administrative region of northwestern Liaoning. It was found that the total area of coniferous forests in the study area is about 6013.67 km², accounting for 9.59% of northwestern Liaoning. The proposed framework has the potential to offer timely and accurate information on coniferous forests and holds promise for informed decision making and the sustainable development of ecological environment.

Accurate estimation of forest carbon stock is critical for understanding ecosystem carbon dynamics and informing climate mitigation strategies. This study presents a deep learning framework that integrates Sentinel-2 multispectral imagery with an enhanced residual neural network for estimating aboveground forest carbon stock in the Liuchong River Basin, Bijie City, Guizhou Province, China. The proposed model incorporates multiscale residual blocks and channel attention mechanisms to improve spatial feature extraction and spectral dependency modeling. A dataset of 150 ground inventory plots was employed for supervised training and validation. Comparative experiments with Random Forest, Gradient Boosting Decision Trees (GBDT), and Vision Transformer (ViT) demonstrate that the enhanced ResNet achieves the best performance, with a root mean square error (RMSE) of 23.02 Mg/ha and a coefficient of determination ($R^2$) of 0.773 on the test set. Spatial mapping results further reveal that the model effectively captures fine-scale carbon stock variations across mountainous forested landscapes. These findings underscore the potential of combining multispectral remote sensing and advanced neural architectures for scalable, high-resolution forest carbon estimation in complex terrain.

As one of the main types of land cover, cultivated land is the direct carrier of food production, and its changes have a very important impact on food security. Timely and accurate acquisition of cultivated land area and distribution information is of great significance to ensuring food security and promoting economic development. Classic semantic segmentation models usually have a large number of training parameters, and there are problems of inaccurate segmentation and low efficiency when performing image segmentation. Moreover, most methods of cultivating land extraction are only applicable to certain specific data sets or specific research areas, and the generalization ability of the model is poor. In response to these problems, this article proposes an improved Deeplab v3+ extraction method. First, the lightweight network MobileNetV2 is used to replace the feature extraction network Xception of the DeepLabv3+ model to reduce the number of model parameters and improve the training speed. Secondly, compare different attention mechanism modules and select SE attention to join the model to enhance the network’s extraction accuracy of cultivated land and improve the accuracy of semantic segmentation of remote sensing images. Finally, transfer learning is introduced, and the feature extraction network trained on the ImageNet data set is used as a pre-training model to enhance the model’s ability to obtain features and improve the network classification accuracy. The results of multi-model comparison experiments on the GID data set show that the method in this paper has excellent segmentation performance. It can effectively solve the problems of varying degrees of misclassification, missing classification and over-segmentation in the segmentation results of classic models, improve the phenomenon of inaccurate boundary and contour segmentation of ground objects, and provide support for subsequent cultivated land extraction tasks.

Farmland shelterbelts are crucial elements in safeguarding agricultural ecological security and sustainable development, with their precise extraction being vital for regional ecological monitoring and precision agriculture management. However, constrained by their narrow linear distribution, complex farmland backgrounds, and spectral confusion issues, traditional remote sensing methods encounter significant challenges in terms of accuracy and generalization capability. In this study, six representative deep learning semantic segmentation models—U-Net, Attention U-Net (AttU_Net), ResU-Net, U²-Net, SwinUNet, and TransUNet—were systematically evaluated for farmland shelterbelt extraction using high-resolution Gaofen-6 imagery. Model performance was assessed through four-fold cross-validation and independent test set validation. The results indicate that convolutional neural network (CNN)-based models show overall better performance than Transformer-based architectures; on the independent test set, the best-performing CNN model (U-Net) achieved a Dice Similarity Coefficient (DSC) of 91.45%, while the lowest DSC (88.86%) was obtained by the Transformer-based TransUNet model. Among the evaluated models, U-Net demonstrated a favorable balance between accuracy, stability, and computational efficiency. The trained U-Net was applied to large-scale farmland shelterbelt mapping in the study area (Alar City, Xinjiang), achieving a belt-level visual accuracy of 95.58% based on 385 manually interpreted samples. Qualitative demonstrations in Aksu City and Shaya County illustrated model transferability. This study provides empirical guidance for model selection in high-resolution agricultural remote sensing and offers a feasible technical solution for large-scale and precise farmland shelterbelt extraction.

Accurate estimation of forest fuel load (FFL) is essential for effective forest management and fire risk assessment. This study presents an approach for estimating FFL in the Greater Khingan Mountains by integrating Sentinel-1 SAR and Sentinel-2 optical data. The combined data provided complementary structural and spectral information, allowing for a more comprehensive analysis of forest characteristics. We evaluated multiple models, including simple linear regression (SLR), multiple linear regression (MLR), Random Forest (RF), XGBoost, and multilayer perceptron (MLP). Results showed that ensemble models, particularly XGBoost and RF, achieved the highest accuracy, with XGBoost attaining the lowest MAE (18.43 t/hm2), lowest RMSE (25.50 t/hm2), and highest R2 (0.86) when using combined data sources. Sentinel-2 data consistently outperformed single-source models, highlighting the value of multi-source data fusion in forest fuel estimation. This methodology is scalable to other regions, offering a robust approach for forest fuel load assessment and enhancing fire risk management. However, the transferability of our approach to different ecological settings requires further consideration. Regional variations in vegetation types, climate conditions, and topography may significantly influence the model’s performance. Additionally, seasonal changes in fuel load distribution could affect prediction accuracy. To address these scalability challenges, future work should explore domain adaptation techniques and model fine-tuning strategies to enhance the generalizability of the proposed method across diverse geographic regions.